Method and device for evaluating quality of pathological slide image

Abstract

A computing device includes at least one memory, and at least one processor configured to analyze at least one object expressed in a pathological slide image, evaluate quality of the pathological slide image based on a result of the analyzing, and perform at least one additional operation according to a result of the evaluating.

What is claimed is: 
     
         1 . A computing device comprising:
 at least one memory; and   at least one processor configured to:   use a machine learning model to identify an analyzable region and a cancer region from a pathological slide image,   generate first quantitative information corresponding to the analyzable region and second quantitative information corresponding to the cancer region,   perform a quality evaluation test of the pathological slide image based on a comparison between the first quantitative information and a first reference value and a comparison between the second quantitative information and a second reference value, and   display on a display device the result of the quality evaluation test indicating whether the pathological slide image has passed the quality evaluation test.   
     
     
         2 . The computing device of  claim 1 , wherein the at least one processor is configured to:
 use the machine learning model to detect a plurality of tissue regions and the cancer region, and   wherein the analyzable region is identified based on the plurality of tissue regions.   
     
     
         3 . The computing device of  claim 1 , wherein the at least one processor is configured to:
 determine that the pathological slide image has passed the quality evaluation test if the first quantitative information is greater than or equal to the first reference value and the second quantitative information is greater than or equal to the second reference value.   
     
     
         4 . The computing device of  claim 1 , wherein the at least one processor is configured to:
 determine that the pathological slide image has failed the quality evaluation test if the first quantitative information is smaller than the first reference value or the second quantitative information is smaller than the second reference value.   
     
     
         5 . The computing device of  claim 1 , wherein the at least one processor is further configured to:
 compare third quantitative information of a biomarker with a third reference value, and   wherein the third quantitative information of the biomarker is related to at least one of a tumor cell, a lymphocyte cell, and tumor purity.   
     
     
         6 . The computing device of  claim 5 , wherein the at least one processor is configured to:
 compare the third quantitative information of the biomarker with the third reference value if the pathological slide image has passed the quality evaluation test.   
     
     
         7 . The computing device of  claim 1 , wherein the at least one processor is further configured to obtain information about the at least one of the analyzable region, the cancer region, and a biomarker by analyzing the pathological slide image with the machine learning model, and control the display device to display the information with the pathological slide image. 
     
     
         8 . The computing device of  claim 1 , wherein the at least one processor is further configured to generate a report comprising the result of the quality evaluation test and a basis of the result. 
     
     
         9 . The computing device of  claim 1 , wherein the at least one processor is further configured to classify regions of the pathological slide image into at least one of the cancer region, a cancer stroma region, a necrosis region, and a background region, and classify a plurality of cells expressed in the pathological slide image into at least one of tumor cells, lymphocyte cells, and other cells. 
     
     
         10 . A method of evaluating a pathological slide image, the method comprising:
 using a machine learning model to identify an analyzable region and a cancer region from a pathological slide image;   generating first quantitative information corresponding to the analyzable region and second quantitative information corresponding to the cancer region;   performing a quality evaluation test of the pathological slide image based on a comparison between the first quantitative information and a first reference value and a comparison between the second quantitative information and a second reference value; and   displaying on a display device the result of the quality evaluation test indicating whether the pathological slide image has passed the quality evaluation test.   
     
     
         11 . The method of  claim 10 , wherein the using of the machine learning model comprises using the machine learning model to detect a plurality of tissue regions and the cancer region, and
 wherein the analyzable region is identified based on the plurality of tissue regions.   
     
     
         12 . The method of  claim 10 , further comprising:
 determining that the pathological slide image has passed the quality evaluation test if the first quantitative information is greater than or equal to the first reference value and the second quantitative information is greater than or equal to the second reference value.   
     
     
         13 . The method of  claim 10 , further comprising:
 determining that the pathological slide image has failed the quality evaluation test if the first quantitative information is smaller than the first reference value or the second quantitative information is smaller than the second reference value.   
     
     
         14 . The method of  claim 10 , further comprising:
 comparing third quantitative information of a biomarker with a third reference value, and   wherein the third quantitative information of the biomarker is related to at least one of a tumor cell, a lymphocyte cell, and tumor purity.   
     
     
         15 . The method of  claim 14 , the comparing of the third quantitative information comprises comparing the third quantitative information of the biomarker with the third reference value if the pathological slide image has passed the quality evaluation test. 
     
     
         16 . The method of  claim 10 , further comprising:
 obtaining information about the at least one of the analyzable region, the cancer region, and a biomarker by analyzing the pathological slide image with the machine learning model, and   wherein the displaying on the display device comprises displaying the information with the pathological slide image.   
     
     
         17 . The method of  claim 10 , further comprising:
 generating a report comprising the result of the quality evaluation test and a basis of the result generate a report comprising the result of the quality evaluation test and a basis of the result.   
     
     
         18 . The method of  claim 10 , further comprising:
 classifying regions of the pathological slide image into at least one of the cancer region, a cancer stroma region, a necrosis region, and a background region, and classify a plurality of cells expressed in the pathological slide image into at least one of tumor cells, lymphocyte cells, and other cells.   
     
     
         19 . A non-transitory computer-readable recording medium having recorded thereon a program for causing a computer to execute the method of  claim 10 .